Food monitoring method and system based on intelligent sample reserving cabinet

Abstract

The invention discloses a food monitoring method and system based on an intelligent sample reserving cabinet, and belongs to the technical field of food sample reserving. The method is applied to the reserved sample cabinet, the reserved sample cabinet is provided with an infrared camera, when trigger information that the reserved sample food is placed in the reserved sample cabinet is obtained, the infrared camera is controlled to collect a first food image of the reserved sample food, operation data of the reserved sample cabinet are obtained, and the operation data comprise operation power, operation time and operation time. According to the first food image, determining feature data of the reserved sample food, the feature data including temperature feature data and category feature data, and according to the operation data, the temperature feature data and the category feature data, determining quality data of the reserved sample food, and sending reserved sample food prompt information according to the quality data and a preset quality value. The method has the beneficial effects of improving the accuracy of reserved sample monitoring data and the standard reaching rate of reserved samples.

Description

Technical Field

[0001] This invention relates to the field of food sample retention technology, and in particular to a food monitoring method and system based on an intelligent sample retention cabinet. Background Technology

[0002] With the improvement of living standards, food safety is crucial to people's quality of life. Currently, food sampling is recorded and managed manually. This manual method is not only inefficient but also cumbersome, making it very difficult to supervise. Problems such as non-standard sampling and unclear records occur at some stages. When sampling is outsourced or performed by part-time personnel, issues such as insufficient sample collection and improper placement are common, leading to inaccurate monitoring data and substandard samples.

[0003] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main objective of this invention is to provide a food monitoring method and system based on an intelligent sample retention cabinet, aiming to improve the accuracy of sample monitoring data and the compliance rate of retained samples. To achieve the above objective, this invention provides a food monitoring method based on an intelligent sample retention cabinet, applied to a sample retention cabinet equipped with an infrared camera. The food monitoring method based on the intelligent sample retention cabinet includes the following steps: When the trigger information for placing the food sample in the sample retention cabinet is received, the infrared camera is controlled to capture the first food image of the food sample and the operating data of the sample retention cabinet is acquired. The operating data includes: operating power. Based on the first food image, characteristic data of the retained food sample is determined, including temperature characteristic data and category characteristic data. The quality data of the retained food samples are determined based on the operational data, the temperature characteristic data, and the category characteristic data. Send a reminder message about the retained food sample based on the quality data and preset quality values.

[0005] Optionally, the step of determining the characteristic data of the retained food sample based on the first food image includes: The first food image is corrected according to a preset processing procedure to obtain the first corrected data. The preset processing procedure includes: noise removal and uniformity correction. The first corrected data is divided into sample partitions according to the image segmentation algorithm to obtain multiple sample partitions; The sample category of each sample partition is identified by image matching, and the corresponding temperature data is determined. The temperature characteristic data is determined based on the temperature data of each sample partition, and the category characteristic data is determined based on the sample category of each sample partition.

[0006] Optionally, the step of dividing the first corrected data into sample partitions according to the image segmentation algorithm to obtain multiple sample partitions includes: Each pixel of the first corrected data is classified according to the clustering algorithm to obtain the first grouped data image; The grouped data image is smoothed to obtain a second grouped data image; The plurality of sample partitions are determined based on the second grouped data image.

[0007] Optionally, the sample retention cabinet is equipped with a color camera, and the step of identifying the sample category of each sample zone through image matching and determining the corresponding temperature data includes: A first matching relationship is obtained by matching the first color image with the sample partition; The color data and texture data of the first color image are extracted based on the first matching relationship; The sample category is determined based on the color data and the texture data; The temperature data is calculated based on the pixel intensity of each sample partition and a first mapping relationship, wherein the first mapping relationship is a mapping relationship between pixel intensity values ​​and temperature values.

[0008] Optionally, the step of determining the quality data of the retained food sample based on the operational data, the temperature characteristic data, and the category characteristic data includes: Determine the cooling capacity corresponding to the target time based on the aforementioned operating data; Calculate the temperature change value within the target time based on the temperature characteristic data; The first specific heat capacity of the sampled food is determined based on the category characteristic data; The mass data is calculated based on the cooling capacity, the temperature change value, and the first specific heat capacity.

[0009] Optionally, the step of sending a sample food reminder message based on the quality data and a preset quality value further includes: Based on the quality data, the number of individual repackaged containers for the retained food samples, and the corresponding repackage ratio, calculate the corresponding sub-mass of each individual repackaged container. When at least one of the sub-masses is less than the preset mass value, a first alarm message is sent. When no sub-quality is less than the preset quality value, the data of the multiple sub-qualitys are saved to the log.

[0010] Optionally, the step of controlling the infrared camera to acquire a first food image of the retained food sample includes: The infrared camera is controlled to acquire first food images of multiple sample foods according to a preset frequency and preset duration.

[0011] Furthermore, to achieve the above objectives, the present invention also provides a food monitoring system based on an intelligent sample retention cabinet, applied to a sample retention cabinet, wherein the food monitoring system based on the intelligent sample retention cabinet includes: The monitoring module is used to control the infrared camera to capture a first food image of the food sample when it receives trigger information that the food sample has been placed in the sample retention cabinet, and to acquire the operating data of the sample retention cabinet, the operating data including: operating power; The identification module is used to determine the feature data of the retained food based on the first food image, the feature data including: temperature feature data and category feature data; The calculation module is used to determine the quality data of the retained food sample based on the operating data, the temperature characteristic data, and the category characteristic data. The prompting module is used to send prompt information about the retained food sample based on the quality data and preset quality values.

[0012] In addition, to achieve the above objectives, the present invention also provides a sample retention cabinet, the sample retention cabinet comprising: a memory, a processor, and a food monitoring program based on the intelligent sample retention cabinet stored on the memory and executable on the processor, the food monitoring program based on the intelligent sample retention cabinet being configured to implement the steps of the food monitoring method based on the intelligent sample retention cabinet described in any of the above claims.

[0013] In addition, to achieve the above objectives, the present invention also provides a storage medium storing a food monitoring program based on an intelligent sample retention cabinet, wherein the food monitoring program based on an intelligent sample retention cabinet, when executed by a processor, implements the steps of the food monitoring method based on an intelligent sample retention cabinet as described above.

[0014] This invention proposes a food monitoring method based on an intelligent sample retention cabinet. This method controls an infrared camera to acquire a first image of the retained food sample and obtains the operating data of the sample retention cabinet. Based on the first food image, it determines the characteristic data of the retained food sample, thereby enabling intelligent monitoring of the condition of the retained food sample and dynamically monitoring its changes. Based on the operating data, temperature characteristic data, and category characteristic data, it determines the quality data of the retained food sample. Compared to manual recording, this method can monitor whether the retained food sample meets standards during the retention process. Based on the quality data and preset quality values, it sends a reminder message for the retained food sample, thereby promptly identifying abnormal samples and improving the accuracy of monitoring data and the compliance rate of retained samples. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the circuit structure of the hardware operating environment sample retention cabinet involved in the embodiment of the present invention; Figure 2 This is a front view of the intelligent sample retention cabinet; Figure 3 This is a side view of the intelligent sample retention cabinet; Figure 4 A top view of the intelligent sample retention cabinet; Figure 5 This is a flowchart illustrating the first embodiment of the food monitoring method based on an intelligent sample retention cabinet of the present invention. Figure 6 This is a schematic diagram of the specific process of step S2 in the second embodiment of the food monitoring method based on intelligent sample retention cabinet of the present invention.

[0016] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0017] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0018] Reference Figure 1 , Figure 1 This is a schematic diagram of the sample retention cabinet circuit structure of the hardware operating environment involved in the embodiment of the present invention.

[0019] like Figure 1 As shown, the sample retention cabinet may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, an interactive device 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The interactive device 1003 may include a display screen and an input unit such as a keyboard. Optionally, the interactive device 1003 may also be connected to the communication bus via standard wired or wireless interfaces. The network interface 1004 may optionally include standard wired or wireless interfaces (such as a Wi-Fi interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0020] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the sample retention cabinet, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0021] Preferably, the sample retention cabinet can be an intelligent sample retention cabinet, with an image acquisition device installed on its surface for facial recognition and recording user on / off data. Preferably, the operation process is recorded via the image acquisition device. For unauthorized use, alert messages and network alarms can be sent.

[0022] Optionally, a pull-out shelf design is adopted to facilitate users' storage and retrieval of food samples. The shelf 101 is placed on the shelf guide rail 102. The shelf 101 is bent 30mm high sheet metal in the front and back, which can act as a handle and prevent the sample box from falling out during the process of pulling out the shelf 101. When the user puts in or takes out the sample box, the shelf 101 can be pulled out halfway to facilitate the user's placement or removal of the sample box. The shelf limiting block 103 limits the pulling distance of the shelf 101 to prevent the shelf from being pulled out too much and tilting.

[0023] Optionally, double-layered LOW-E glass doors can be used to improve the condensation problem in high-temperature and high-humidity environments; Optionally, it is equipped with an emergency door opening function to solve the problem of retrieving food samples in the event of a power outage; Optionally, it can be equipped with stainless steel shelves and individual storage compartments; Optionally, preferably, a 120° door opening angle is set to prevent the door from being dented.

[0024] You can refer to Figure 2 , Figure 3 as well as Figure 4 , Figure 2 This is a front view of the intelligent sample retention cabinet. Figure 3 This is a side view of the intelligent sample retention cabinet. Figure 4 This is a top view of the intelligent sample retention cabinet. It includes: shelf 101, guide rail 102, shelf limiting block 103, double-layer glass 104, screen assembly 105, water basin 106, weighing module 107, printer 108, screen cover assembly lock 109, screen cover assembly guide rail 1010, display screen cover assembly 1011, door lock latch 1012, and door angle limiting block 1013.

[0025] like Figure 1 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a data storage module, a network communication module, a user interface module, and a food monitoring program based on the intelligent sample retention cabinet.

[0026] exist Figure 1In the sample retention cabinet shown, the network interface 1004 is mainly used for data communication with other devices; the interactive device 1003 is mainly used for data interaction with the user; the processor 1001 and memory 1005 in the food monitoring device based on the intelligent sample retention cabinet of the present invention can be set in the sample retention cabinet. The sample retention cabinet calls the food monitoring program based on the intelligent sample retention cabinet stored in the memory 1005 through the processor 1001 and executes the food monitoring method based on the intelligent sample retention cabinet provided in the embodiment of the present invention.

[0027] This invention provides a food monitoring method based on an intelligent sample retention cabinet, referring to... Figure 5 , Figure 2 This is a flowchart illustrating the first embodiment of a food monitoring method based on an intelligent sample retention cabinet according to the present invention.

[0028] In this embodiment, the method is applied to a sample retention cabinet, which is equipped with an infrared camera. The food monitoring method based on the intelligent sample retention cabinet includes the following steps: Step S1: When the trigger information of placing the food sample in the sample retention cabinet is obtained, the infrared camera is controlled to capture the first food image of the food sample and the operating data of the sample retention cabinet is obtained. The operating data includes: operating power. In this embodiment, the method of obtaining information about the placement of food samples in the retention cabinet is not limited. Specifically, it can be through user input and saving information, sensor detection, or the opening status of the retention cabinet. Preferably, an infrared camera can be used to capture a first food image of the food samples, and the presence of food samples in the retention cabinet can be determined based on the first food image. This allows for the continuous acquisition of multiple first food images in real time. When the food samples are removed, the corresponding information can be obtained promptly. In this embodiment, the operating data may also include cooling efficiency. When different cooling zones exist in some retention cabinets, the cooling capacity corresponding to each cooling zone can also be obtained. Here, the first food image is an infrared image.

[0029] Step S2: Determine the characteristic data of the retained food sample based on the first food image. The characteristic data includes: temperature characteristic data and category characteristic data. In this embodiment, the type of the sampled food is determined by analyzing the first food image, and the category feature data is obtained. It should be noted that the first food image can include multiple different types of feature data. The temperature feature data is obtained by calculating the corresponding temperature based on the pixel depth of each different type of food image. It should be further noted that since there can be multiple first food images, for example, the first food images can be acquired at a frequency of once per minute, and the corresponding temperature can be calculated by extracting the pixel depth of food images in the same area. This allows for the generation of a temperature change curve for the sampled food. Preferably, the temperature feature data here is the temperature change rate, i.e., the slope of the temperature change curve of the sampled food. Preferably, without using other data, the first food image can be used to identify it as a liquid or solid category; optionally, the specific heat capacity of water can be used as the specific heat capacity of the liquid category, and the specific heat capacity of meat can be used as the specific heat capacity of the solid category. Preferably, a color camera can also be used to distinguish the various category features in the first food image by acquiring color images.

[0030] Step S3: Determine the quality data of the retained food sample based on the operating data, the temperature characteristic data, and the category characteristic data; Specifically, the specific heat capacity is determined based on the category characteristic data, and the quality data of the retained food sample is calculated based on the operating data, the temperature characteristic data, and the specific heat capacity corresponding to the category characteristic data. Furthermore, an optimization coefficient can be set using historically collected data to improve the calculated quality data of the retained food sample.

[0031] Step S4: Send a sample food reminder message based on the quality data and preset quality value.

[0032] Preferably, the preset mass value here can be 125 grams, or it can be data from other food sample retention standards. When the mass value is greater than or equal to the preset mass value, a message indicating sufficient sample retention is sent; when the mass value is greater than or equal to the preset mass value, a message indicating insufficient sample retention is sent. In this implementation, it can be ensured that the quality of the food samples entering the sample retention cabinet meets the testing requirements, thereby improving the accuracy of the sample retention cabinet monitoring.

[0033] In this embodiment, an infrared camera is controlled to acquire a first food image of the retained food sample and obtain the operating data of the retention cabinet. Based on the first food image, the characteristic data of the retained food sample are determined, thereby enabling intelligent monitoring of the retained food sample in the retention cabinet and dynamic monitoring of its changes. Based on the operating data, the temperature characteristic data, and the category characteristic data, the quality data of the retained food sample is determined. Compared with manual recording, this method can monitor whether the retained food sample meets the standards during the retention process. Based on the quality data and preset quality values, a retention food reminder message is sent, thereby enabling timely identification of abnormal retention and improving the accuracy of monitoring data and the compliance rate of retained samples.

[0034] Furthermore, based on the first embodiment, a second embodiment of the food monitoring method based on an intelligent sample retention cabinet of the present invention is proposed. In this embodiment, reference is made to... Figure 6 The step of determining the characteristic data of the retained food based on the first food image includes: Step S21: Correct the first food image according to the preset processing flow to obtain the first correction data. The preset processing flow includes: noise removal and uniformity correction. In this embodiment, the preset processing flow includes: removing noise from the first food image, correcting distortion caused by the lens, and removing irrelevant image areas. Specifically, by calculating the temperature difference between the temperature corresponding to the pixels in the first food image and the internal temperature of the sample retention cabinet, it is determined whether the food sample is newly placed in the sample retention cabinet based on the temperature difference.

[0035] Step S22: Divide the first corrected data into sample partitions according to the image segmentation algorithm to obtain multiple sample partitions; In this embodiment, clustering segmentation or edge extraction methods can be used to divide the first corrected data into sample partitions, thereby obtaining multiple sample partitions. In other embodiments, a deep learning model can also be used to divide the first corrected data to obtain the multiple sample partitions.

[0036] Step S23: Identify the sample category of each sample partition through image matching and determine the corresponding temperature data; By identifying the characteristics of each sample partition, the corresponding sample type can be determined, such as the edge features of each sample partition and the presence of gaps. The temperature data is based on the average temperature of each pixel within the neighborhood of the geometric center of each sample partition. The neighborhood is a 5×5 window centered at the geometric center. This neighborhood can be set by the user or engineer.

[0037] Step S24: Determine the temperature feature data based on the temperature data of each sample partition, and determine the category feature data based on the sample category of each sample partition.

[0038] In this embodiment, the temperature data of each sample partition is directly used as the temperature feature data. Preferably, the change in temperature data of each sample partition over time is used as the temperature feature data, thereby saving subsequent storage resources; that is, storing one feature value saves storage space than storing a set of feature values. The category feature data can be the corresponding label information and specific heat capacity.

[0039] In this embodiment, the first food image is corrected according to a preset processing flow to obtain first corrected data. The first corrected data is divided into sample partitions according to an image segmentation algorithm, which can accurately monitor the placement of the samples and effectively distinguish the placement of different food samples, resulting in multiple sample partitions. The sample category of each sample partition is identified by image matching, and the corresponding temperature data is determined. The temperature feature data is determined based on the temperature data of each sample partition, and the category feature data is determined based on the sample category of each sample partition, thereby realizing dynamic monitoring of the retained samples.

[0040] Furthermore, the step of dividing the first corrected data into sample partitions according to the image segmentation algorithm to obtain multiple sample partitions includes: Each pixel of the first corrected data is classified according to the clustering algorithm to obtain the first grouped data image; The grouped data image is smoothed to obtain a second grouped data image; The plurality of sample partitions are determined based on the second grouped data image.

[0041] In this embodiment, a pixel vector is constructed corresponding to the position coordinates and depth information of each pixel in the image, resulting in multiple pixel vectors. A clustering space is then built, comprising these pixel vectors. The K-means algorithm is used to group these pixel vectors, and an image is assembled based on the position coordinates according to the grouping results, thus obtaining a first grouped data image. Specifically, a closing operation is performed on the first grouped data image to obtain a second grouped data image. Here, the closing operation refers to performing image dilation followed by image erosion.

[0042] In this embodiment, each pixel of the first corrected data is classified by a clustering algorithm to obtain a first grouped data image. The grouped data image is then smoothed to obtain a second grouped data image, thereby improving the accuracy of the grouping.

[0043] Furthermore, based on the first or second embodiment, a third embodiment of the food monitoring method based on an intelligent sample retention cabinet of the present invention is proposed. In this embodiment, the sample retention cabinet is equipped with a color camera, and the step of identifying the sample category of each sample zone through image matching and determining the corresponding temperature data includes: A first matching relationship is obtained by matching the first color image with the sample partition; The color data and texture data of the first color image are extracted based on the first matching relationship; The sample category is determined based on the color data and the texture data; The temperature data is calculated based on the pixel intensity of each sample partition and a first mapping relationship, wherein the first mapping relationship is a mapping relationship between pixel intensity values ​​and temperature values.

[0044] In this embodiment, the color camera refers to a visible light camera. The purpose of matching the first color image with the sample partition to obtain the first matching relationship is to accurately combine color data and texture data with the sample partition, thereby improving the accuracy of identifying the sample category.

[0045] Furthermore, based on the above embodiments, a fourth embodiment of the food monitoring method based on an intelligent sample retention cabinet of the present invention is proposed. In this embodiment, the step of determining the quality data of the retained food based on the operating data, the temperature characteristic data, and the category characteristic data includes: Determine the cooling capacity corresponding to the target time based on the aforementioned operating data; Calculate the temperature change value within the target time based on the temperature characteristic data; The first specific heat capacity of the sampled food is determined based on the category characteristic data; The mass data is calculated based on the cooling capacity, the temperature change value, and the first specific heat capacity.

[0046] In this embodiment, the cooling capacity is determined based on the operating power, the cooling efficiency, and the target time. An equation for calculating the mass data is constructed based on the cooling capacity, the temperature change value, and the first specific heat capacity. The result of the equation is then calculated and solved. Specifically, the calculation formula is as follows:

[0047] Where P represents the cooling capacity, and here... Here, c represents the target time, and c represents the first specific heat capacity. This represents the temperature change value.

[0048] In this embodiment, the cooling capacity corresponding to the target time period is determined by the operational data, the temperature change value within the target time period is calculated based on the temperature characteristic data, the first specific heat capacity of the sampled food is determined based on the category characteristic data, and the mass data is calculated based on the cooling capacity, the temperature change value, and the first specific heat capacity. This improves the accuracy of the mass data.

[0049] Furthermore, based on the above embodiments, a fifth embodiment of the food monitoring method based on an intelligent sample retention cabinet of the present invention is proposed, wherein the step of sending sample food reminder information according to the quality data and preset quality value further includes: Based on the quality data, the number of individual repackaged containers for the retained food samples, and the corresponding repackage ratio, calculate the corresponding sub-mass of each individual repackaged container. When at least one of the sub-masses is less than the preset mass value, a first alarm message is sent. When no sub-quality is less than the preset quality value, the data of the multiple sub-qualitys are saved to the log.

[0050] It should be noted that, according to the food sample retention standards for catering services, sample containers should be sealed, appropriately sized, and dedicated, with sample labels, and stored in a clean environment. Sample bags and boxes, which are easy to observe and handle, are preferable. Therefore, if opaque, individually packaged containers that are not easily observable are used, the sample retention cabinet can send a second alarm message to prompt the user to adjust the container type as required. In this embodiment, glass containers, plastic containers, and aseptic bags can be rotated to preserve the sampled food.

[0051] Furthermore, the step of controlling the infrared camera to acquire the first food image of the retained food sample includes: The infrared camera is controlled to acquire first food images of multiple sample foods according to a preset frequency and preset duration.

[0052] In this embodiment, the preset frequency can be set by the user, and can detect the first food image of the sampled food within 10 minutes within a certain time period.

[0053] Furthermore, this invention also proposes a food monitoring system based on an intelligent sample retention cabinet, applied to a sample retention cabinet. The food monitoring system based on the intelligent sample retention cabinet includes: The monitoring module is used to control the infrared camera to capture a first food image of the food sample when it is detected that the food sample is placed in the sample retention cabinet, and to obtain the operating data of the sample retention cabinet, the operating data including: operating power; The identification module is used to determine the feature data of the retained food based on the first food image, the feature data including: temperature feature data and category feature data; The calculation module is used to determine the quality data of the retained food sample based on the operating data, the temperature characteristic data, and the category characteristic data. The prompting module is used to send prompt information about the retained food sample based on the quality data and preset quality values.

[0054] Furthermore, embodiments of the present invention also propose a sample retention cabinet, the sample retention cabinet comprising: a memory, a processor, and a food monitoring program based on the intelligent sample retention cabinet stored on the memory and executable on the processor, the food monitoring program based on the intelligent sample retention cabinet being configured to implement the steps of the food monitoring method based on the intelligent sample retention cabinet described above.

[0055] Furthermore, embodiments of the present invention also propose a storage medium storing a food monitoring program based on an intelligent sample retention cabinet, wherein the food monitoring program based on an intelligent sample retention cabinet, when executed by a processor, implements the steps of the food monitoring method based on an intelligent sample retention cabinet as described above.

[0056] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0057] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0058] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0059] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A food monitoring method based on an intelligent sample retention cabinet, characterized in that, Applied to a sample retention cabinet equipped with an infrared camera, the food monitoring method based on an intelligent sample retention cabinet includes the following steps: When the trigger information for placing the food sample in the sample retention cabinet is received, the infrared camera is controlled to capture the first food image of the food sample and the operating data of the sample retention cabinet is acquired. The operating data includes: operating power. Based on the first food image, characteristic data of the retained food sample is determined, including temperature characteristic data and category characteristic data. The quality data of the retained food samples are determined based on the operational data, the temperature characteristic data, and the category characteristic data. Send a reminder message about the retained food sample based on the quality data and preset quality values.

2. The food monitoring method based on an intelligent sample retention cabinet as described in claim 1, characterized in that, The step of determining the characteristic data of the retained food based on the first food image includes: The first food image is corrected according to a preset processing procedure to obtain the first corrected data. The preset processing procedure includes: noise removal and uniformity correction. The first corrected data is divided into sample partitions according to the image segmentation algorithm to obtain multiple sample partitions; The sample category of each sample partition is identified by image matching, and the corresponding temperature data is determined. The temperature characteristic data is determined based on the temperature data of each sample partition, and the category characteristic data is determined based on the sample category of each sample partition.

3. The food monitoring method based on an intelligent sample retention cabinet as described in claim 2, characterized in that, The step of dividing the first corrected data into sample partitions according to the image segmentation algorithm to obtain multiple sample partitions includes: Each pixel of the first corrected data is classified according to the clustering algorithm to obtain the first grouped data image; The grouped data image is smoothed to obtain a second grouped data image; The plurality of sample partitions are determined based on the second grouped data image.

4. The food monitoring method based on an intelligent sample retention cabinet as described in claim 2, characterized in that, The sample retention cabinet is equipped with a color camera. The step of identifying the sample category of each sample zone through image matching and determining the corresponding temperature data includes: A first matching relationship is obtained by matching the first color image with the sample partition; The color data and texture data of the first color image are extracted based on the first matching relationship; The sample category is determined based on the color data and the texture data; The temperature data is calculated based on the pixel intensity of each sample partition and a first mapping relationship, wherein the first mapping relationship is a mapping relationship between pixel intensity values ​​and temperature values.

5. The food monitoring method based on an intelligent sample retention cabinet as described in claim 1, characterized in that, The step of determining the quality data of the retained food sample based on the operational data, the temperature characteristic data, and the category characteristic data includes: Determine the cooling capacity corresponding to the target time based on the aforementioned operating data; Calculate the temperature change value within the target time based on the temperature characteristic data; The first specific heat capacity of the sampled food is determined based on the category characteristic data; The mass data is calculated based on the cooling capacity, the temperature change value, and the first specific heat capacity.

6. The food monitoring method based on an intelligent sample retention cabinet as described in claim 1, characterized in that, The step of sending a sample food reminder message based on the quality data and the preset quality value further includes: Based on the quality data, the number of individual repackaged containers for the retained food samples, and the corresponding repackage ratio, calculate the corresponding sub-mass of each individual repackaged container. When at least one of the sub-masses is less than the preset mass value, a first alarm message is sent. When no sub-quality is less than the preset quality value, the data of the multiple sub-qualitys are saved to the log.

7. The food monitoring method based on an intelligent sample retention cabinet as described in any one of claims 1 to 6, characterized in that, The step of controlling the infrared camera to acquire the first food image of the retained food sample includes: The infrared camera is controlled to acquire first food images of multiple sample foods according to a preset frequency and preset duration.

8. A food monitoring system based on an intelligent sample retention cabinet, characterized in that, The food monitoring system based on the intelligent sample retention cabinet, applied to sample retention cabinets, includes: The monitoring module is used to control the infrared camera to capture a first food image of the food sample when it receives trigger information that the food sample has been placed in the sample retention cabinet, and to acquire the operating data of the sample retention cabinet, the operating data including: operating power; The identification module is used to determine the feature data of the retained food based on the first food image, the feature data including: temperature feature data and category feature data; The calculation module is used to determine the quality data of the retained food sample based on the operating data, the temperature characteristic data, and the category characteristic data. The prompting module is used to send prompt information about the retained food sample based on the quality data and preset quality values.

9. A sample retention cabinet, characterized in that, The sample retention cabinet includes: a memory, a processor, and a food monitoring program based on the intelligent sample retention cabinet stored on the memory and executable on the processor, the food monitoring program based on the intelligent sample retention cabinet being configured to implement the steps of the food monitoring method based on the intelligent sample retention cabinet as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores a food monitoring program based on an intelligent sample retention cabinet, which, when executed by a processor, implements the steps of the food monitoring method based on an intelligent sample retention cabinet as described in any one of claims 1 to 7.

Images